The phenomenal growth of online Flash movies in recent years has made Flash one of the most prevalent media formats on the
Web. The retrieval and management issues of Flash, vital to the utilization of the enormous Flash resource, are unfortunately
overlooked by the research community. This paper presents the first piece of work (to the best of our knowledge) in this domain
by suggesting an integrated framework for the retrieval of Flash movies based on their content characteristics as well as
contextual information. The proposed approach consists of two major components: (1) a content-based retrieval component, which
explores the characteristics of Flash movie content at compositional and semantic levels; and (2) a context-based retrieval
component, which explores the contextual information including the texts and hyperlinks surrounding the movies. An experimental
Flash search engine system has been implemented to demonstrate the feasibility of the suggested framework.
Keywords Flash movies - content and context based retrieval - content characteristics - contextual information - Flash search engine
The work described in this paper was supported substantially by a grant (Project No. 7001457), and partially by another grant
(Project No. 7001564), both from CityU of Hong Kong.